Saved in:
Bibliographic Details
Main Authors: Leite, Pedro H. L., Valadares, Pedro Benevenuto, Biscainho, Luiz W. P.
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.30457
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917545032810496
author Leite, Pedro H. L.
Valadares, Pedro Benevenuto
Biscainho, Luiz W. P.
author_facet Leite, Pedro H. L.
Valadares, Pedro Benevenuto
Biscainho, Luiz W. P.
contents Regional accent classification in Brazilian Portuguese (pt-BR) suffers from the need for reliable labeling. While large self-supervised learning (SSL) speech models are powerful, their training pipelines dilute sociophonetic information, since accent labels are generally not reliable or are not used in training objectives. This work introduces a novel workflow for feature extraction using only acoustic labels. By isolating explicit regional accent landmarks and using a phoneme-based forced aligner (ZIPA), our targeted feature set captures dialectal variance more effectively than utterance embeddings, demonstrating that localized features can outperform general-purpose architectures on accent-related tasks using minimal and objective data labels.
format Preprint
id arxiv_https___arxiv_org_abs_2605_30457
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Extracting accent features in spoken Brazilian Portuguese without sociolinguistic labels
Leite, Pedro H. L.
Valadares, Pedro Benevenuto
Biscainho, Luiz W. P.
Audio and Speech Processing
Computation and Language
Regional accent classification in Brazilian Portuguese (pt-BR) suffers from the need for reliable labeling. While large self-supervised learning (SSL) speech models are powerful, their training pipelines dilute sociophonetic information, since accent labels are generally not reliable or are not used in training objectives. This work introduces a novel workflow for feature extraction using only acoustic labels. By isolating explicit regional accent landmarks and using a phoneme-based forced aligner (ZIPA), our targeted feature set captures dialectal variance more effectively than utterance embeddings, demonstrating that localized features can outperform general-purpose architectures on accent-related tasks using minimal and objective data labels.
title Extracting accent features in spoken Brazilian Portuguese without sociolinguistic labels
topic Audio and Speech Processing
Computation and Language
url https://arxiv.org/abs/2605.30457